fix(session): trigger semantic indexing for parent directory after memory extraction

[qin-ctx]

Description

Extracted memories were not searchable via vector search because the parent directory's .abstract.md/.overview.md (level 0/1) were never generated after memory extraction, making them invisible to the hierarchical retriever's global search phase.

Related Issue

Fixes #422

Type of Change

• Bug fix (non-breaking change that fixes an issue)

Changes Made

• openviking/session/compressor.py: Add _enqueue_semantic_for_parent() call in _index_memory() to trigger parent directory semantic generation (.abstract.md/.overview.md) after every memory indexing operation. This ensures the hierarchical retriever can discover the directory at level 0/1 and then drill into level-2 memory files.
• openviking/session/memory_extractor.py: Remove duplicate _enqueue_semantic_for_parent() calls from _merge_tool_memory() and _merge_skill_memory(), since _index_memory() in the compressor now handles this uniformly for all memory types.

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• My changes generate no new warnings
• Any dependent changes have been merged and published

Additional Notes

Root cause: The search system uses hierarchical retrieval -- it first searches directory-level summaries (.abstract.md at level 0/1), then drills into matched directories to find actual files (level 2). Resource ingestion correctly triggers the full SemanticQueue -> SemanticProcessor pipeline, but memory extraction only enqueued the memory file itself (level 2) to EmbeddingQueue, skipping the parent directory semantic generation step.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}